© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155546
    Prev
    Next
    INDEX
    Explanations

    fi

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    フェ
    0.51
    ﻓ
    0.46
     Bev
    0.43
    ฟ
    0.43
    پے
    0.42
     MenuView
    0.41
     Eyre
    0.41
    <0x86>
    0.41
    fe
    0.40
    FE
    0.40
    POSITIVE LOGITS
    ègre
    0.44
     sil
    0.39
    ژن
    0.37
    sil
    0.37
    lif
    0.37
    ion
    0.36
    lim
    0.36
    iston
    0.36
    istic
    0.36
    biotic
    0.36
    Activations Density 0.000%

    No Known Activations